agentleFS
blixvipblixvip/skills/5/SKILL.md

5

Skill4 starsChanged 3 months agoMITView on GitHub

Maximum normal execution timebox for complex tasks that should still be completed quickly. Use when the user invokes /5 and target completion within 25 minutes.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a concise internal execution path and begin implementation quickly.

    line 17
  2. Distinctive:

    Run the strongest relevant verification available.

    line 22
  3. Distinctive:

    Test connected functionality for regressions.

    line 23
  4. Distinctive:

    Remove dead code, temporary workarounds, and debugging artifacts introduced during the task.

    line 25
  5. Distinctive:

    Avoid unrelated feature work or perfectionism.

    line 26
  6. Distinctive:

    Use parallel work where possible: investigation + implementation + testing + verification.

    line 28
  7. Distinctive:

    If the task genuinely cannot be completed inside the timebox because of an external blocker, complete as much verified work as possible and …

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/5 — Full

Take full ownership of this task and drive it to a completed, verified state.

Timebox

Target completion in under 25 minutes. This is the largest normal execution window, not permission to work slowly. Quality remains the same as every other level.

Behavior

  • Investigate thoroughly enough to understand the affected system.
  • Create a concise internal execution path and begin implementation quickly.
  • Handle cross-file and cross-component changes when required.
  • Resolve root causes instead of symptoms.
  • Make necessary architectural improvements when they materially improve correctness.
  • Cover important edge cases, failure states, and integration boundaries.
  • Run the strongest relevant verification available.
  • Test connected functionality for regressions.
  • Iterate on failures until the implementation works.
  • Remove dead code, temporary workarounds, and debugging artifacts introduced during the task.
  • Avoid unrelated feature work or perfectionism.

Use parallel work where possible: investigation + implementation + testing + verification. Do not spend the timebox narrating progress; spend it producing the result.

If the task genuinely cannot be completed inside the timebox because of an external blocker, complete as much verified work as possible and report the exact blocker rather than continuing indefinitely.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.